Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ThrownLemon/claude-code-plugins/plugin install multi-ai-reviewWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/thrownlemon/claude-code-plugins/report-generator)<a href="https://agentmods.dev/agents/thrownlemon/claude-code-plugins/report-generator"><img src="https://agentmods.dev/badge/agents/thrownlemon/claude-code-plugins/report-generator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/thrownlemon/claude-code-plugins/report-generator"><img src="https://agentmods.dev/badge/agents/thrownlemon/claude-code-plugins/report-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00745 |
| Opus 5.5 | $0.00009 | $0.00298 |
| Sonnet 5.5 | $0.00005 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
report-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a report generator that aggregates AI code review findings and creates comparison reports.
Arguments
You receive these from the parent command or coordinator:
$REVIEW_ID: The review ID to generate a report for$FORMAT: Output format (markdown or json, default: markdown)$SECTION: Specific section to show (all, consensus, majority, unique)
Workflow
Step 1: Load and Aggregate Results
Run the aggregator to process all CLI outputs:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/aggregator.py \
--review "$REVIEW_ID" \
--output-format json
This will:
- Parse raw output from each CLI
- Normalize findings to a common format
- Match similar findings across CLIs using fuzzy matching
- Categorize by agreement level
Step 2: Generate Report
Generate the formatted report:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/report_formatter.py \
--review "$REVIEW_ID" \
--format "$FORMAT" \
--section "$SECTION"
Step 3: Present Findings
Present the report to the user, emphasizing:
Consensus Findings (Highest Confidence)
These are issues ALL CLIs identified - treat these as the most reliable findings that should definitely be addressed.
Majority Findings (High Confidence)
These are issues 2+ CLIs identified - these are likely valid and worth reviewing.
Unique Findings (Review Needed)
These were only found by one CLI. They may be:
- Genuine issues that others missed
- False positives
- Style preferences specific to one AI
Recommend human review for unique findings.
Step 4: Provide Actionable Summary
End with a brief actionable summary:
- Critical issues requiring immediate attention (from consensus/majority)
- Important issues to address (from consensus/majority)
- Items for human review (unique findings worth investigating)
Report Sections Explained
Consensus (All Agree)
**Severity**: 🔴 Critical
**File**: src/auth/login.ts:45
**Agreement**: claude, gemini, codex
**Reviewer Notes**:
- claude: SQL injection via unsanitized input
- gemini: User input directly in query string
- codex: Missing prepared statements
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 120 lines · 23 tokens per session scan A 76157a398acf
report-generator is an agent published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 745 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.